Moore’s Law is an observation first made by the co-founder of Fairchild Semiconductors and Intel, Gordon Moore. The initial version of Moore’s Law, created in 1965, called for the number of transistors in a chip to double every year. In the 1970’s, Moore was forced to revise the observation and changed it to say that the number of transistors would double every other year. Current Intel CEO Pat Gelsinger says that the pace has slowed down to the point where we can expect the number of transistors in a chip to double every three years.
Gelsinger said during his talk, “I think we’ve been declaring the death of Moore’s Law for about three to four decades.” And while that might be true, he did admit that “we’re no longer in the golden era of Moore’s Law, it’s much, much harder now, so we’re probably doubling effectively closer to every three years now, so we’ve definitely seen a slowing.” Intel’s CEO is pushing a “Super Moore’s Law” concept based on using 2.5D and 3D chip packaging to increase transistor counts. Gelsinger also refers to this as “Moore’s Law 2.0.”
Gelsinger also said that by 2030, Intel could create a chip sporting one trillion transistors. Four things that the CEO mentioned could make it happen include RibbonFET transistors. Like the Gate-All-Around transistors currently used by Samsung Foundy with its 3nm production, with RibbonFET the gate covers all four sides of the channel reducing current leaks and increasing the drive current.
Gerlsinger also points out that the economics of the business have changed recently. “A modern fab seven or eight years ago would have cost about $10 billion,” he said. “Now, it costs about $20 billion, so you’ve seen a different shift in the economics.”